Use it to implement, review, or document LinkedIn data snapshots, change events, OAuth access, and read-only profile tools for Unlinked.

It clarifies token handling, permissions, consent errors, and the fact that the API is currently limited to members in the European Economic Area and Switzerland.

How larsbaunwall/Unlinked configures Claude Code and Codex

Q: What is linkedin-member-data-portability?

A guide for using LinkedIn’s Member Data Portability API, which lets eligible members access their own professional profile and experience data through an AI assistant. It applies to the Unlinked local MCP server and read-only data access.

Reuse

Borrowing it

Nothing to install: this file belongs to larsbaunwall/Unlinked. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/larsbaunwall/Unlinked/main/.agents/skills/linkedin-member-data-portability/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/larsbaunwall/Unlinked

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/larsbaunwall/unlinked/linkedin-member-data-portability/github.svg)](https://agentmods.dev/skills/larsbaunwall/unlinked/linkedin-member-data-portability)

Your own site

<a href="https://agentmods.dev/skills/larsbaunwall/unlinked/linkedin-member-data-portability"><img src="https://agentmods.dev/badge/skills/larsbaunwall/unlinked/linkedin-member-data-portability/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/larsbaunwall/unlinked/linkedin-member-data-portability"><img src="https://agentmods.dev/badge/skills/larsbaunwall/unlinked/linkedin-member-data-portability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,185 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00053	$0.02185
Opus 5.5	$0.00021	$0.00874
Sonnet 5.5	$0.00011	$0.00437
Haiku 4.5	$0.00005	$0.00218

Measured 1mo ago against content hash 7f3244bdcaaa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

linkedin-member-data-portability scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/linkedin-member-data-portability/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LinkedIn Member Data Portability API

Use this skill whenever you implement or review LinkedIn API behavior for Unlinked.

Product Context

Unlinked uses LinkedIn's Member Data Portability (Member) API product. The purpose is to let a LinkedIn member connect their own professional profile and experience data to an AI assistant through a local MCP server. The API is read-only for this project.

This API product exists for DMA data portability and is currently available only to LinkedIn members located in the European Economic Area and Switzerland. User-facing setup and error messages should say this plainly.

Access And Tokens

A LinkedIn Developer application must be provisioned with Member Data Portability API (Member).
LinkedIn's OAuth Token Generator docs currently instruct users to request r_dma_portability_self_serve for member self-serve access.
Snapshot and changelog docs also reference r_dma_portability_member and r_dma_portability_3rd_party permissions. Treat 403 responses as likely product/scope/consent problems and explain that clearly.
The access token comes from the LINKEDIN_TOKEN environment variable (never a tool input). Send it only as Authorization: Bearer <access_token> to LinkedIn.
Never store, log, return, or include access tokens in thrown errors, CLI output or cache files.
LinkedIn data (not the token) is cached for a bounded time (default 6 h, memory for MCP, memory plus owner-only disk files for the CLI). Cache only sanitized data: redacted, normalized snapshot rows and cleaned changelog events. See AGENTS.md.

Required Headers

Every LinkedIn REST call should include:

Authorization: Bearer <access_token>
Linkedin-Version: <YYYYMM>
Content-Type: application/json

Use the exact header name Linkedin-Version. The version is pinned to 202312: live, no other value is accepted, even though the docs have newer versions. Do not make it configurable.

Snapshot API

Use the Snapshot API for profile and professional-history data.

Read the full file on GitHub · 159 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago Changed · +16 lines 7f3244bdcaaa
2mo ago First seen · 143 lines · 53 tokens per session scan A 4c2a384e30b0

Subscribe to this mod's changes

linkedin-member-data-portability is a skill published in the GitHub repository larsbaunwall/Unlinked (4 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 2,185 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Backend and APIs linkedin mcp-server

linkedin-member-data-portability next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
linkedin-member-data-portabilitylarsbaunwall/Unlinked	Skill	4	1mo ago	MIT	A	53	Claude Code, Codex
n8n-code-toolczlonkowski/n8n-mcp	Skill	23k	yesterday	MIT	A	221	Claude Code, Codex
n8n-subworkflowsczlonkowski/n8n-mcp	Skill	23k	yesterday	MIT	A	121	Claude Code, Codex
td-api-referencedylanroscover/Embody	Skill	212	2d ago	MIT	A	48	Claude Code
sanity-singletonssanity-io/agent-toolkit	Skill	197	10d ago	MIT	A	90	Claude Code
sanity-best-practicessanity-io/agent-toolkit	Skill	197	10d ago	MIT	A	177	Claude Code
tech-specsgriddynamics/rosetta	Skill	370	yesterday	Apache-2.0	A	23	Claude Code

Unlinked: Skill for Claude Code